project-knowledge-maintainer

project-knowledge-maintainer is a skill for Claude Code, Codex from chancy24/codex-knowledge-base-skill. It costs 33 tokens per session (1,136 once invoked), scanned A, original, MIT.

A project knowledge base maintained through AGENTS.md and organized knowledge files. It records a project’s purpose, architecture, decisions, bugs, interfaces, and recent changes for coding agents.

In plain words
What is it for?
Use it to initialize or update project documentation, preserve bug fixes, record decisions, document APIs or schemas, and organize development notes.
Why use it?
It prevents every new agent session from having to rediscover project context, past fixes, and important technical decisions.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/chancy24/codex-knowledge-base-skill/project-knowledge-maintainer
Any agent
npx skills add chancy24/codex-knowledge-base-skill --skill project-knowledge-maintainer
Clone the repo
git clone --depth 1 https://github.com/chancy24/codex-knowledge-base-skill

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,136 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.01136
Opus 5 $0.00016 $0.00568
Sonnet 5 $0.00007 $0.00227
Haiku 4.5 $0.00003 $0.00114

Measured 3d ago against content hash f5bc37e1cb42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-knowledge-maintainer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/project-knowledge-maintainer/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Knowledge Maintainer

Purpose

Use this Skill to initialize, maintain, and evolve a project-level knowledge base for AI coding agents. The knowledge base helps future agent sessions understand project purpose, architecture, interfaces, decisions, bugs, and recent changes without rediscovering everything from scratch.

Keep the workflow tool-neutral. It should be usable by Codex, Claude Code, Cursor, Gemini CLI, and other coding agents that can read project files and follow repository-local instructions.

When To Use

Use this Skill when the user asks to:

  • initialize a project knowledge base
  • summarize or document a project
  • fix a bug and preserve the repair experience
  • add or change a feature
  • add or change an API, schema, command, or data format
  • record a technical decision or tradeoff
  • organize raw project materials into structured knowledge
  • review or retrospect a completed development session
  • update AGENTS.md or files under knowledge/

Inputs

Common inputs include:

  • The current repository or target project path.
  • Existing project files, source code, docs, issues, logs, or raw materials.
  • The user's current task and any implementation changes made during the session.
  • Existing AGENTS.md, knowledge/, raw/, or skills/ content if present.

Outputs

Expected outputs include:

  • AGENTS.md project rules.
  • knowledge/overview.md project overview.
  • knowledge/business.md business logic and usage scenarios.
  • knowledge/architecture.md system architecture and data flow.
  • knowledge/api.md interfaces, schemas, commands, and data structures.
  • knowledge/decisions.md technical decisions and tradeoffs.
  • knowledge/bugs.md bug history, root causes, fixes, and prevention rules.
  • knowledge/changelog.md session-level change records.
  • Optional raw/ and project-local skills/ folders.
  • A short final report listing what was updated and what still needs verification.

Workflow

  1. Read project rules first:
    • AGENTS.md if present.
    • knowledge/overview.md
    • knowledge/architecture.md
    • knowledge/decisions.md
    • knowledge/bugs.md
  2. If initializing a repository, use the templates in references/templates/ or run the initializer script from this package.
  3. Understand the current task and identify what changed:
    • project goal or business logic
    • architecture or module boundaries
    • API, command, data file, schema, or return structure
    • bug symptom, root cause, fix, or prevention rule
    • technical decision or tradeoff
    • user-facing behavior or UI convention
  4. Update only the relevant knowledge files.
  5. Remove or reconcile duplicate, stale, or contradictory content.
  6. Always update knowledge/changelog.md after important work.
  7. Report the updated files and any missing validation.

Read the full file on GitHub · 143 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 143 lines · 33 tokens per session scan A f5bc37e1cb42

Subscribe to this mod's changes

project-knowledge-maintainer is a skill published in the GitHub repository chancy24/codex-knowledge-base-skill (1 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 1,136 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

karpathy-llm-wiki

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

Astro-Han/karpathy-llm-wiki · 67 tokens

nopua

The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行').…

wuji-labs/nopua · 90 tokens

weave

Parallel strand orchestration — decompose a task into 3+ independently scoped strands, fan out real subagents (worktree-isolated when they write files), and coordinate through a session file and Insight Capsules. Use ONLY when the user explicitly invokes it by name or slash command.

entropyvortex/meta-llm-charter · 59 tokens

mcp-media-inbox-triage

Find media, partnership, and high-intent requests buried in a shared Gmail inbox, summarize the useful ones, and route them to the right owner through Zapier MCP.

zapier/gtm-cheat-codes · 43 tokens

customer-deck-builder

Build tailored customer-facing sales or customer success decks from approved account context and generate the presentation with Gamma through Zapier MCP.

zapier/gtm-cheat-codes · 29 tokens

premortem

First-principles premortem on a high-stakes plan: assume failure 6–18 months out, reconstruct causal death chains, surface hidden assumptions, deliver a revised reversibility-weighted plan. Use ONLY when the user explicitly invokes it by name or slash command.

entropyvortex/meta-llm-charter · 59 tokens